Pierre Marion
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
AI×1
Frequent co-authors
Research Timeline
2026
Distilling LLM Feedback for Lean Theorem Proving
The paper introduces Feedback Distillation, a novel training method that uses a language model's privileged feedback to provide token-level supervision, significantly improving complex reasoning tasks like Lean theorem-proving compared to standard RL methods like GRPO.
Highlighted terms show continued research focus across papers
Papers
cs.AIRecentMay 29, 2026
Distilling LLM Feedback for Lean Theorem Proving
Gaetan Narozniak, Gérard Biau, Rémi Munos, Ahmad Rammal +1 more
The paper introduces Feedback Distillation, a novel training method that uses a language model's privileged feedback to provide token-level supervision, significantly improving complex reasoning tasks…
View →